6 citations · 13 across the 13 of their papers we have counts for
17 papers
Cognitive Thermometers: Machine Learning and Logical Complexity
Shane Steinert-Threlkeld, Jakub Szymanik
How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and compl…
Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages
C. M. Downey, Terra Blevins, Nora Goldfine +1
Pre-trained multilingual language models underpin a large portion of modern NLP tools outside of English. A strong baseline for specializing these models for specific languages is…
Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages
Shunjie Wang, Shane Steinert-Threlkeld
Despite the fact that Transformers perform well in NLP tasks, recent studies suggest that self-attention is theoretically limited in learning even some regular and context-free lan…
The Weighted Möbius Score: A Unified Framework for Feature Attribution
Yifan Jiang, Shane Steinert-Threlkeld
Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended featur…
Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis
Pangbo Ban, Yifan Jiang, Tianran Liu +1
To what extent do pre-trained language models grasp semantic knowledge regarding the phenomenon of distributivity? In this paper, we introduce DistNLI, a new diagnostic dataset for…
Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models
David K. Yi, James V. Bruno, Jiayu Han +2
We investigate the extent to which verb alternation classes, as described by Levin (1993), are encoded in the embeddings of Large Pre-trained Language Models (PLMs) such as BERT, R…